{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:16Z","timestamp":1780949176824,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3698160","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:57:01Z","timestamp":1780084621000},"page":"83044-83054","source":"Crossref","is-referenced-by-count":0,"title":["ATP-VLA: A Robust Grasping Framework Driven by Temporal Asymmetric Multimodal Fusion and Representation Isomorphism"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2978-3552","authenticated-orcid":false,"given":"Haocong","family":"Duan","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7807-9929","authenticated-orcid":false,"given":"Guangsen","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9126-1787","authenticated-orcid":false,"given":"Jinyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8309-9745","authenticated-orcid":false,"given":"Meile","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2827-0323","authenticated-orcid":false,"given":"Zhongwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Weifang University of Science and Technology, Shouguang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"229","author":"Brohan"},{"key":"ref2","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"270","author":"Kim"},{"key":"ref3","volume-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref4","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Driess"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref6","first-page":"6892","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. ICRA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.063"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref9","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref10","article-title":"ACoT-VLA: Action chain-of-thought for vision-language-action models","author":"Zhong","year":"2026","journal-title":"arXiv:2601.11404"},{"key":"ref11","article-title":"Audio-VLA: Adding contact audio perception to vision-language-action model for robotic manipulation","author":"Wei","year":"2025","journal-title":"arXiv:2511.09958"},{"key":"ref12","article-title":"OmniVLA: Physically-grounded multimodal VLA with unified multi-sensor perception for robotic manipulation","author":"Guo","year":"2025","journal-title":"arXiv:2511.01210"},{"key":"ref13","first-page":"1368","article-title":"See, hear, and feel: Smart sensory fusion for robotic manipulation","volume-title":"Proc. CoRL, PMLR","volume":"205","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/s17122762"},{"key":"ref15","first-page":"314","article-title":"The feeling of success: Does touch sensing help predict grasp outcomes?","volume-title":"Proc. CoRL","volume":"78","author":"Calandra"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794298"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01034"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref21","first-page":"14961","article-title":"See, hear, explore: Curiosity via audio-visual association","volume-title":"Proc. NeurIPS","volume":"33","author":"Dean"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref24","volume-title":"Theory and Applications of Digital Speech Processing","author":"Rabiner","year":"2010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/504729.504754"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.090"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","volume":"139","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aav3123"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref38","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023","journal-title":"arXiv:2311.01378"},{"key":"ref39","article-title":"Foundation models in robotics: Applications, challenges, and the future","author":"Firoozi","year":"2023","journal-title":"arXiv:2312.07843"},{"key":"ref40","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv:2307.05973"},{"issue":"2","key":"ref41","article-title":"Cross-modal visuo-tactile object recognition","volume":"7","author":"Li","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref43","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018","journal-title":"arXiv:1801.08757"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342481"},{"key":"ref45","volume-title":"\u03c00: A vision-language-action flow model for general robot control","author":"Black","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3650584"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3609980"},{"key":"ref48","article-title":"CogACT: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024","journal-title":"arXiv:2411.19650"},{"key":"ref49","article-title":"TacVLA: Contact-aware tactile fusion for robust vision-language-action manipulation","author":"Zhang","year":"2026","journal-title":"arXiv:2603.12665"},{"key":"ref50","article-title":"VLA-touch: Enhancing vision-language-action models with dual-level tactile feedback","author":"Bi","year":"2025","journal-title":"arXiv:2507.17294"},{"key":"ref51","article-title":"OmniVTLA: Vision-tactile-language-action model with semantic-aligned tactile sensing","author":"Cheng","year":"2025","journal-title":"arXiv:2508.08706"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246722"},{"key":"ref53","article-title":"AcoustiGrasp: Multimodal acoustic-visual fusion for dexterous robotic grasping under occlusion","author":"Y\u0131ld\u0131z","year":"2025","journal-title":"Preprint"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11540079.pdf?arnumber=11540079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:53:28Z","timestamp":1780948408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11540079\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3698160","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}